利用多模态机器学习改进盖亚视差博士研究员
More data, more and better distances: Improving on Gaia parallaxes with multi-modal machine learning
原帖优先：申请材料、截止时间与资格以原帖和学校官方说明为准。
博士招生与资助公告
- 申请年度
- 2027；原帖说明：How to apply Apply now You need to: • choose programme type (Research), 2027/28, Faculty of Engineering and Physical Sciences • select Full time or Part time • search for programme PhD Physics (7089) • add name of the supervisor in section 2 of the application Applications should include: • your CV (resumé) • 2 academic references • degree transcripts and certificates to date • English language qualification (if applicable)
- 最近申请截止
- 2027-01-06
- 全部申请截止
- （Europe/London）
- 资助原文
- Fees and funding We offer a range of funding opportunities for both UK and international students. Horizon Europe fee waivers automatically cover the difference between overseas and UK fees for qualifying students. Competition-based Presidential Bursaries from the University cover the difference between overseas and UK fees for top-ranked applicants. Competition-based studentships offered by our schools typically cover UK-level tuition fees and a stipend for living costs for top-ranked applicants. Funding will be awarded on a rolling basis, so apply early for the best opportunity to be considered. For more information, please visit our postgraduate research funding pages.
- 资助条件
- 原帖为竞争性或附条件资助说明，未确认本项目获资助及申请人能获奖；不作为保证全奖。
- 原帖材料说明
- • your CV (resumé)
- • 2 academic references
- • degree transcripts and certificates to date
- • English language qualification (if applicable)
确定性信息来自对应版本的完整原帖。原帖只提供日期，日末和学校当地时区为本站转换假设。筛选使用最后申请截止；资助与录取以学校审核结果为准。
AI 中文速览
- 研究内容
- 本项目旨在开发一个结合多种天文观测数据的神经网络，用于在盖亚视差不确定或缺失的情况下估计恒星距离，并改善现有估计，从而推进恒星天体物理学并发展机器学习方法。
- 申请条件
- 申请者需持有英国2:1荣誉学士学位或其国际同等学历，具备机器学习经验高度受喜.
- 待遇
- 学校为英国及国际学生提供一系列资助机会，包括地平线欧洲学费减免、总统奖学金以及涵盖英国本土学费和生活津贴的竞争性奖学金。
- 申请方式
- 申请人需通过学校在线系统申请，选择研究型项目、2027/28学年、工程与物理科学学院，选择全职或兼职，搜索PhD Physics (7089)项目，并在申请表的第二部分添加导师姓名。
- 材料清单
- 简历（CV）
- 2封学术推荐信
- 至今的学位成绩单与证书
- 英语语言资格证明（如适用）
由 gemini-2.5-flash-lite 生成，博士岗判定置信度 100%。
岗位信息
- 最终轮次截止
- 2027-01-06
- 学科
- 物理与天文
- 合同类型
- 项目资助
- 本站收录
- 内容更新
- 原帖导师候选（待核验）
- Poshak Gandhi, Christian Knigge
- 来源
- 南安普顿大学博士研究项目招生 · 最近核对 2026-10-24
- 详情核验
判定依据（原文摘录）
- 这是一项博士（PhD）培养机会
Type of degree Doctor of Philosophy
- 明确的截止日期
Closing date 6 Jan 2027
- 入学要求包含2:1学位
A UK 2:1 honours degree, or its international equivalent.
原文
View all current projects
Postgraduate research project
More data, more and better distances: Improving on Gaia parallaxes with multi-modal machine learning
Funding
Competition funded
Competition funded
View fees and funding
Type of degree
Doctor of Philosophy
Entry requirements
2:1 honours degree
2:1 honours degree
View full entry requirements
Faculty graduate school
Faculty of Engineering and Physical Sciences
Closing date
6 Jan 2027
On this page
About the project
Potential supervisors
Entry requirements
Fees and funding
How to apply
Contact us
About the project
Potential supervisors
Entry requirements
Fees and funding
How to apply
Contact us
About the project
Accurate stellar distances underpin our understanding of the Galaxy. This project will develop a neural network that combines diverse astronomical observations to estimate distances, even when Gaia parallaxes are uncertain or missing, and improve existing estimates. It will advance stellar astrophysics while developing machine learning methods with applications beyond astronomy.
The Gaia mission has recently provided photometric (brightness) and astrometric (positional) information for nearly 2 billion astronomical objects. Perhaps most importantly, it has provided parallaxes -- and hence allowed distance estimates -- for roughly 1.5 billion sources. However, only about 10% of these have "good" parallaxes sufficient for inferring distances robustly.
In this project, we will develop, train and exploit a machine learning algorithm that will provide useful distances estimate even for sources with highly uncertain Gaia parallaxes -- or perhaps no parallaxes at all. At the same time, it will also improve the quality of the distance estimate for sources that do have good-quality parallaxes.
The core idea is that almost every astronomical measurement contains at least some information about the distance to that source. For example, distant sources will appear fainter, whereas sources located behind dense interstellar clouds may be closer than they appear.
We will develop and train a neural network combines source observations to provide the best possible distance estimate for the source. Machine-learning algorithms that can work with different kinds of data simultaneously are known as "multi-modal", and they are extremely powerful tools for extracting critical information hidden in complex data sets.
The specific distance-estimation tool we aim to develop will be immensely valuable to stellar astrophysics. The machine learning methodology we will learn about, implement and exploit has an even wider range of applicability, well beyond the astronomical context.
The School of Physics and Astronomy is committed to promoting equality, diversity inclusivity as demonstrated by our Athena SWAN award. We welcome all applicants regardless of their gender, ethnicity, disability, sexual orientation or age, and will give full consideration to applicants seeking flexible working patterns and those who have taken a career break. The University has a generous maternity policy, onsite childcare facilities, and offers a range of benefits to help ensure employees’ well-being and work-life balance. The University of Southampton is committed to sustainability and has been awarded the Platinum EcoAward.
Potential supervisors
Lead supervisor
Professor Poshak Gandhi
Professor of Astrophysics
Research interests
• Data-intensive Astronomy
• Time-domain astrophysics, Black Holes, Lunar astronomy
• Novel survey techniques on anything in the cosmos, really.
Supervisors
Professor Christian Knigge
Professor of Astrophysics
Research interests
• accretion phenomena and associated outflows
• cataclysmic variables
• close binaries
Entry requirements
A UK 2:1 honours degree, or its international equivalent.
Experience with machine learning is highly desirable.
Fees and funding
We offer a range of funding opportunities for both UK and international students. Horizon Europe fee waivers automatically cover the difference between overseas and UK fees for qualifying students.
Competition-based Presidential Bursaries from the University cover the difference between overseas and UK fees for top-ranked applicants.
Competition-based studentships offered by our schools typically cover UK-level tuition fees and a stipend for living costs for top-ranked applicants.
Funding will be awarded on a rolling basis, so apply early for the best opportunity to be considered.
For more information, please visit our postgraduate research funding pages.
How to apply
Apply now
You need to:
• choose programme type (Research), 2027/28, Faculty of Engineering and Physical Sciences
• select Full time or Part time
• search for programme PhD Physics (7089)
• add name of the supervisor in section 2 of the application
Applications should include:
• your CV (resumé)
• 2 academic references
• degree transcripts and certificates to date
• English language qualification (if applicable)
Contact us
Faculty of Engineering and Physical Sciences
For questions about applying, email our Doctoral College (doctoralcollege-admissions@soton.ac.uk).
Project leader
For an initial conversation, email Professor Poshak Gandhi (poshak.gandhi@soton.ac.uk).